Instructions to use l3utterfly/phi-2-layla-v1-chatml with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use l3utterfly/phi-2-layla-v1-chatml with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="l3utterfly/phi-2-layla-v1-chatml", trust_remote_code=True)
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("l3utterfly/phi-2-layla-v1-chatml", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("l3utterfly/phi-2-layla-v1-chatml", trust_remote_code=True)
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Inference
Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use l3utterfly/phi-2-layla-v1-chatml with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "l3utterfly/phi-2-layla-v1-chatml"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "l3utterfly/phi-2-layla-v1-chatml",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/l3utterfly/phi-2-layla-v1-chatml

SGLang

How to use l3utterfly/phi-2-layla-v1-chatml with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "l3utterfly/phi-2-layla-v1-chatml" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "l3utterfly/phi-2-layla-v1-chatml",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "l3utterfly/phi-2-layla-v1-chatml" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "l3utterfly/phi-2-layla-v1-chatml",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use l3utterfly/phi-2-layla-v1-chatml with Docker Model Runner:
```
docker model run hf.co/l3utterfly/phi-2-layla-v1-chatml
```

5B merge?

by EloyOn - opened Apr 6, 2024

Discussion

EloyOn

Apr 6, 2024

Have you considered merging this model up to 5B to see if it improves significantly?
That size might work well having into account smarphones RAM and CPU limitations.
Something similar to this: https://huggingface.co/dillfrescott/sonya-medium

l3utterfly

Owner Apr 6, 2024

I haven’t much experience with creating merges to be honest. I’ll explore that when I have some free time.

If you have experience with creating merges, please feel free to do so with Layla models!

EloyOn

Apr 6, 2024

•

edited Apr 6, 2024

Sadly I don't T_T If I had a good computer I would spend all the time trying that probably xDDD
Seems they use this mergekit: https://github.com/arcee-ai/mergekit

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

· Sign up or log in to comment